Systems and methods for enhancing search using semantic search results

Abstract

Embodiments of the present disclosure provide systems and methods for enhancing search using semantic search results. A semantic search engine performs a semantic search to identify documents semantically related to a search query. A search query to perform a second type of search is received. The second type of search is scoped to content identified in the previous semantic search.

What is claimed is: 
     
         1 . A computer-implemented method for searching electronic documents, comprising:
 receiving a semantic search query from a user to semantically search a document corpus;   servicing the semantic search query to return a first search result, the first search result identifying first documents from the document corpus that are determined to be semantically relevant to the semantic search query;   receiving a second search query from the user to perform a second type of search the document corpus; and   servicing the second search query to perform the second type of search scoped to the first documents to return a second search result.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the second type of search is a lexical query. 
     
     
         3 . The computer-implemented method of  claim 1 , further comprises:
 providing the first search result to the user in a graphical user interface; and   receiving, via user interaction with the graphical user interface, an indication to scope the second type of search to the first documents.   
     
     
         4 . The computer-implemented method of  claim 1 , further comprising automatically scoping the second type of search to the first documents. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein servicing the semantic search query comprises:
 sending a request to a large language model, the request comprising a prompt to the large language model, the prompt comprising the semantic search query;   receiving generative text generated by the large language model in response to the prompt; and   including the generative text with the first search result.   
     
     
         6 . The computer-implemented method of  claim 5 , wherein the request to the large language model includes context to constrain the large language model to the first documents when generating the generative text. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the first search result comprises citations, the citations including chunks of text from the first documents. 
     
     
         8 . A non-transitory, computer-readable medium storing thereon document analysis code executable by a processor, the document analysis code comprising instructions for:
 receiving a semantic search query from a user to semantically search a document corpus;   servicing the semantic search query to return a first search result, the first search result identifying first documents from the document corpus that are determined to be semantically relevant to the semantic search query;   receiving a second search query from the user to perform a second type of search the document corpus; and   servicing the second search query to perform the second type of search scoped to the first documents to return a second search result.   
     
     
         9 . The non-transitory, computer-readable medium of  claim 8 , wherein the second type of search is a lexical search. 
     
     
         10 . The non-transitory, computer-readable medium of  claim 8 , wherein the document analysis code further comprises instructions for:
 providing the first search result to the user in a graphical user interface; and   receiving, via user interaction with the graphical user interface, an indication to scope the second type of search to the first documents.   
     
     
         11 . The non-transitory, computer-readable medium of  claim 8 , wherein the document analysis code further comprises instructions for:
 automatically scoping the second type of search to the first documents.   
     
     
         12 . The non-transitory, computer-readable medium of  claim 8 , wherein servicing the semantic search query comprises:
 sending a request to a large language model, the request comprising a prompt to the large language model, the prompt comprising the semantic search query;   receiving generative text generated by the large language model in response to the prompt; and   including the generative text with the first search result.   
     
     
         13 . The non-transitory, computer-readable medium of  claim 12 , wherein the request to the large language model includes context to constrain the large language model to the first documents when generating the generative text. 
     
     
         14 . The non-transitory, computer-readable medium of  claim 8 , wherein the first search result comprises citations, the citations including chunks of text from the first documents. 
     
     
         15 . A computer system proving enhanced search, the computer system comprising:
 storage storing:
 a plurality of snippets, each of the plurality of snippets comprising snippet text extracted from a document in a document corpus and a reference to the document from which the snippet text of that snippet was extracted; 
 an embedding store comprising a vector index of the plurality of snippets; 
   a processor;   a semantic search engine executable to perform semantic searching of the document corpus using the vector index;   a lexical search engine executable to perform lexical searching of the document corpus; and   a user interface, wherein the user interface is executable to scope lexical searches by the lexical search engine to documents identified in semantic search results from the semantic search engine.   
     
     
         16 . The computer system of  claim 15 , wherein:
 the semantic search engine is executable to:
 search the vector index using an embedded query string from a first search input to identify, from the plurality of snippets, semantically relevant snippets that are semantically relevant to the first search input; and 
 return a corresponding semantic search result to the user interface, the corresponding semantic search result comprising document identifiers from the semantically relevant snippets, the document identifiers from the semantically relevant snippets identifying documents from the document corpus; and 
   the user interface is executable to generate a lexical search request to the lexical search engine to perform a corresponding lexical search, the lexical search request comprising search criteria input by a user and the document identifiers from the semantically relevant snippets to scope the corresponding lexical search to the documents identified by the document identifiers from the semantically relevant snippets.   
     
     
         17 . The computer system of  claim 16 , wherein the user interface is executable to:
 display the corresponding semantic search result to the user; and   receive, based on a user interaction with the user interface, an indication from the user to scope the corresponding lexical search to the documents identified by the document identifiers from the semantically relevant snippets.   
     
     
         18 . The computer system of  claim 17 , wherein the corresponding semantic search result comprises a plurality of citations and wherein the indication to scope the corresponding lexical search comprises a selection of one or more citations from the plurality of citations, wherein each of the one or more citations corresponds to one of semantically relevant snippets. 
     
     
         19 . The computer system of  claim 18 , wherein the user interface is executable to:
 automatically scope the corresponding lexical search to the documents identified by the document identifiers from the semantically relevant snippets.   
     
     
         20 . The computer system of  claim 16 , wherein the corresponding semantic search result comprises generative text generated by a large language model based on the semantically relevant snippets.